基于用户行为的产品垃圾评论者检测研究

doi:10.3969/j.issn.1000-3428.2012.11.077

计算机工程 ›› 2012, Vol. 38 ›› Issue (11): 254-257,261.doi: 10.3969/j.issn.1000-3428.2012.11.077

基于用户行为的产品垃圾评论者检测研究

邱云飞，王建坤，邵良杉，刘大有

(辽宁工程技术大学软件学院，辽宁葫芦岛 125105)

收稿日期:2011-12-05 出版日期:2012-06-05 发布日期:2012-06-05
作者简介:邱云飞(1976－)，男，副教授、博士，主研方向：数据挖掘；王建坤，硕士研究生；邵良杉、刘大有，教授、博士生导师
基金项目:
国家自然科学基金资助项目(70971059)；辽宁省高等学校创新团队支持计划基金资助项目(2009T045)；辽宁省科技攻关计划基金资助项目(2007308003)

Research on Product Review Spammer Detection Based on Users’ Behavior

QIU Yun-fei, WANG Jian-kun, SHAO Liang-shan, LIU Da-you

QIU Yun-fei, WANG Jian-kun, SHAO Liang-shan, LIU Da-you

Received:2011-12-05 Online:2012-06-05 Published:2012-06-05

摘要/Abstract

摘要： 为找到垃圾评论的制造者，提出一种基于用户行为的产品垃圾评论者检测方法。从垃圾评论者的行为目的出发，将其发表垃圾评论的5种行为模式作为垃圾评论者的检测指标，从卓越亚马逊网站获取1 470个评论用户，按单指标选取、5个指标集成选取的方法确定最可能和最不可能成为垃圾评论者的评论用户各25个，并对这50个评论者进行人工标记，根据标记结果设计有监督的线性回归模型。实验结果表明，该模型从1 470个评论者中发现88个用户为垃圾评论者，对垃圾评论者的检测效果优于基于用户有用性投票的基准方法。

关键词: 用户行为, 线性回归模型, 垃圾评论者检测, 短文本, 产品评论, 垃圾评论

Abstract: In order to find the review spammers, this paper proposes a user review spammer detecting method that is based on users’ behavior. Starting from the purpose of review spammers, it makes spammer’s five behavior patterns as the index of spammer detection. Based on the 1 470 reviewers, it gets from the JOYO Amazon website, according to a single indicator selection and 5 indicators integration selection, finally gets the 25 of most likely spammers and 25 of the most unlikely spammers, and markes artificially the 50 of suspicious reviewers, according to the artificial results trained a supervised linear regression model which is based on the 5 indicators. Experimental results show that the model of the spammer detection finds 88 review spammers in the 1 470 reviewers, and is more effective than those based on user voting usefulness of the baseline method.

Key words: user behavior, linear regression model, review spammer detection, short text, product review, review spam

中图分类号:

TP311.52

邱云飞, 王建坤, 邵良杉, 刘大有. 基于用户行为的产品垃圾评论者检测研究[J]. 计算机工程, 2012, 38(11): 254-257,261.

QIU Yun-Fei, WANG Jian-Kun, SHAO Liang-Sha, LIU Da-Wei. Research on Product Review Spammer Detection Based on Users’ Behavior[J]. Computer Engineering, 2012, 38(11): 254-257,261.

参考文献

[1] Becchetti L, Castillo C, Donato D, et al. Link Analysis for Web Spam Detection[EB/OL]. (2010-11-21). http://www.chato.cl/ papers/becchetti_2007_link_analysis_web_spam_detection.pdf.
[2] Chirita P A, Diederich J, Nejdl W. MailRank: Using Ranking for Spam Detection[C]//Proc. of the 14th ACM International Con- ference on Information and Knowledge Management. New York, USA: [s. n.], 2005.
[3] Benevenuto F, Magno G, Rodrigues T, et al. Detecting Spammers on Twitter[C]//Proc. of Anti-abuse and Spam Conference on Collaboration, Electronic Messaging. [S. l.]: IEEE Press, 2010.
[4] 何海红. 一种适应短文本的相关测度及其应用[J]. 计算机工程, 2009, 35(6): 88-90.
[5] 孙升芸, 田萱. 产品垃圾评论检测研究综述[J]. 计算机科学, 2011, 38(10): 198-201.
[6] 何苑, 谭红叶. 基于多结构特征的垃圾博客识别研究[J]. 计算机工程与设计, 2010, 31(22): 4932-4935.
[7] Gilbert E, Karahalios K. Understanding Deja Reviewers[C]//Proc. of ACM Conference on Computer Supported Cooperative Work. New York, USA: [s. n.], 2010.
[8] Dellarocas C. Immunizing Online Reputation Reporting Systems Against Unfair Ratings and Discriminatory Behavior[C]//Proc. of the 2nd ACM Conference on Electronic Commerce. New York, USA: [s. n.], 2000. (下转第261页)
[9] Wu Guangyu, Greene D, Smyth B, et al. Distortion As a Validation Criterion in the Identification of Suspicious Reviews[EB/OL]. (2010-11-21). http://www.csi.ucd.ie/content/distortion-validation- criterion-identification-suspicious-reviews.
[10] Mizil C D N, Kossinets G, Kleinberg J, et al. How Opinions are Received by Online Communities: A Case Study on Amazon.com Helpfulness Votes[C]//Proc. of the 18th International Conference on World Wide Web. New York, USA: [s. n.], 2009.
[11] Lim E P, Nguyen V A, Jindal N, et al. Detecting Product Review Spammers Using Rating Behaviors[C]//Proc. of the 19th ACM International Conference on Information and Knowledge Management. New York, USA: [s. n.], 2010.
[12] J?arvelin K, Kek?al?ainen J. IR Evaluation Methods for Retrieving Highly Relevant Documents[C]//Proc. of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, USA: [s. n.], 2000.
[13] Bos W, Tarnai C. Content Analysis in Empirical Social Research[J]. International Journal of Educational Research, 1999, 31(8): 659- 671.
[14] Kassarijian H H. Content Analysis in Consumer Research[J]. Journal of Consumer Research, 1977, 4(1): 8-18.

[1]	段丹丹, 唐加山, 温勇, 袁克海. 基于BERT模型的中文短文本分类算法[J]. 计算机工程, 2021, 47(1): 79-86.
[2]	丁辰晖, 夏鸿斌, 刘渊. 融合知识图谱与注意力机制的短文本分类模型[J]. 计算机工程, 2021, 47(1): 94-100.
[3]	李志, 宋礼鹏. 基于用户窗口行为的内部威胁检测研究[J]. 计算机工程, 2020, 46(4): 135-142,150.
[4]	毕猛, 邵中, 徐剑. 一种用于网络用户行为聚类的标签自动生成方法[J]. 计算机工程, 2020, 46(10): 81-87.
[5]	张光杰, 叶海洋, 王晓锋. 基于多尺度虚拟化的卫星终端用户行为仿真[J]. 计算机工程, 2019, 45(8): 165-172,189.
[6]	李志欣,兰丹媚,张灿龙,唐素勤. 基于Co-Training的微博垃圾评论识别方法[J]. 计算机工程, 2018, 44(7): 212-218.
[7]	殷亚博,杨文忠,杨慧婷,许超英. 基于卷积神经网络和KNN的短文本分类算法研究[J]. 计算机工程, 2018, 44(7): 193-198.
[8]	缪峰,贾华丁,熊于宁. 基于服务相似度的移动用户近似邻居选取方法[J]. 计算机工程, 2018, 44(5): 162-167,173.
[9]	朱正伟,刘晨,黄晓竹,刁小敏. 基于用户行为的智能手机能耗优化方法[J]. 计算机工程, 2018, 44(5): 286-290.
[10]	荆琪,段利国,李爱萍,赵谦. 基于维基百科的短文本相关度计算[J]. 计算机工程, 2018, 44(2): 197-202.
[11]	周飞,高茂庭. 基于PageRank的网络社区意见领袖发现算法[J]. 计算机工程, 2018, 44(2): 203-209,219.
[12]	杨凤芹,宋美佳,孙铁利,孙红光. 面向中文产品评论的完整评价对象抽取方法[J]. 计算机工程, 2017, 43(6): 169-176.
[13]	李晓红,曹林,宿云,马慧芳. 融合统计信息与语义相似度的特征扩展算法[J]. 计算机工程, 2017, 43(6): 177-181.
[14]	胡计鹏,谭励,杨明华,张亚明. 一种基于可信密码模块的用户行为度量方法[J]. 计算机工程, 2017, 43(5): 121-128.
[15]	朱颢东,丁温雪,杨立志,冯嘉美. 微博环境下基于用户行为与主题相似度的改进PageRank算法[J]. 计算机工程, 2017, 43(5): 179-184.

基于用户行为的产品垃圾评论者检测研究

Research on Product Review Spammer Detection Based on Users’ Behavior

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10